arXiv Analytics

Sign in

arXiv:1406.3474 [cs.CV]AbstractReferencesReviewsResources

Heterogeneous Multi-task Learning for Human Pose Estimation with Deep Convolutional Neural Network

Sijin Li, Zhi-Qiang Liu, Antoni B. Chan

Published 2014-06-13Version 1

We propose an heterogeneous multi-task learning framework for human pose estimation from monocular image with deep convolutional neural network. In particular, we simultaneously learn a pose-joint regressor and a sliding-window body-part detector in a deep network architecture. We show that including the body-part detection task helps to regularize the network, directing it to converge to a good solution. We report competitive and state-of-art results on several data sets. We also empirically show that the learned neurons in the middle layer of our network are tuned to localized body parts.

Related articles: Most relevant | Search more
arXiv:1604.07904 [cs.CV] (Published 2016-04-27)
Image Colorization Using a Deep Convolutional Neural Network
arXiv:1509.05371 [cs.CV] (Published 2015-09-17)
DeXpression: Deep Convolutional Neural Network for Expression Recognition
arXiv:1703.03372 [cs.CV] (Published 2017-03-09)
LesionSeg: Semantic segmentation of skin lesions using Deep Convolutional Neural Network